A nonfeasible gradient projection recurrent neural network for equality-constrained optimization problems

Barbarosou, MP; Maratos, NG

dc.contributor.author	Barbarosou, MP	en
dc.contributor.author	Maratos, NG	en
dc.date.accessioned	2014-03-01T01:27:46Z
dc.date.available	2014-03-01T01:27:46Z
dc.date.issued	2008	en
dc.identifier.issn	1045-9227	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/18564
dc.subject	Constrained optimization	en
dc.subject	Convergence	en
dc.subject	Convex and nonconvex problems	en
dc.subject	Recurrent neural networks	en
dc.subject.classification	Computer Science, Artificial Intelligence	en
dc.subject.classification	Computer Science, Hardware & Architecture	en
dc.subject.classification	Computer Science, Theory & Methods	en
dc.subject.classification	Engineering, Electrical & Electronic	en
dc.subject.other	Constraint theory	en
dc.subject.other	Global optimization	en
dc.subject.other	Image classification	en
dc.subject.other	Network protocols	en
dc.subject.other	Neural networks	en
dc.subject.other	Optimization	en
dc.subject.other	Problem solving	en
dc.subject.other	Recurrent neural networks	en
dc.subject.other	Reinforcement learning	en
dc.subject.other	Sensor networks	en
dc.subject.other	Vegetation	en
dc.subject.other	Accurate	en
dc.subject.other	Constrained optimization problems	en
dc.subject.other	Convergence	en
dc.subject.other	Convex and nonconvex problems	en
dc.subject.other	Convex optimization problems	en
dc.subject.other	Efficient	en
dc.subject.other	Exponential convergence rates	en
dc.subject.other	Global convergences	en
dc.subject.other	Gradient projections	en
dc.subject.other	Local convergences	en
dc.subject.other	Neural-network	en
dc.subject.other	Nonconvex	en
dc.subject.other	Numerical results	en
dc.subject.other	Optimization problems	en
dc.subject.other	Tangent spaces	en
dc.subject.other	Constrained optimization	en
dc.subject.other	algorithm	en
dc.subject.other	article	en
dc.subject.other	artificial neural network	en
dc.subject.other	computer simulation	en
dc.subject.other	feedback system	en
dc.subject.other	mathematical computing	en
dc.subject.other	theoretical model	en
dc.subject.other	Algorithms	en
dc.subject.other	Computer Simulation	en
dc.subject.other	Feedback	en
dc.subject.other	Models, Theoretical	en
dc.subject.other	Neural Networks (Computer)	en
dc.subject.other	Numerical Analysis, Computer-Assisted	en
dc.title	A nonfeasible gradient projection recurrent neural network for equality-constrained optimization problems	en
heal.type	journalArticle	en
heal.identifier.primary	10.1109/TNN.2008.2000993	en
heal.identifier.secondary	http://dx.doi.org/10.1109/TNN.2008.2000993	en
heal.language	English	en
heal.publicationDate	2008	en
heal.abstract	In this paper, a recurrent neural network for both convex and nonconvex equality-constrained optimization problems is proposed, which makes use of a cost gradient projection onto the tangent space of the constraints. The proposed neural network constructs a generically nonfeasible trajectory, satisfying the constraints only as t → infin;. Local convergence results are given that do not assume convexity of the optimization problem to be solved. Global convergence results are established for convex optimization problems. An exponential convergence rate is shown to hold both for the convex case and the nonconvex case. Numerical results indicate that the proposed method is efficient and accurate. © 2008 IEEE.	en
heal.publisher	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC	en
heal.journalName	IEEE Transactions on Neural Networks	en
dc.identifier.doi	10.1109/TNN.2008.2000993	en
dc.identifier.isi	ISI:000260119900001	en
dc.identifier.volume	19	en
dc.identifier.issue	10	en
dc.identifier.spage	1665	en
dc.identifier.epage	1677	en